trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02004891936324632,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01002445968162316,
      "grad_norm": 0.27810075879096985,
      "learning_rate": 2.969926620955131e-05,
      "loss": 0.0283,
      "step": 500
    },
    {
      "epoch": 0.02004891936324632,
      "grad_norm": 0.32781505584716797,
      "learning_rate": 2.939853241910261e-05,
      "loss": 0.0244,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 49878,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}